MCP-handle  by WeatherPal-AI

AI-Agent integration and orchestration platform

Created 2 months ago
278 stars

Top 93.6% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

MCP-Handle addresses the complexity of AI agent development by providing a unified platform for orchestrating tooling and managing integrations. It targets AI-agent developers, enabling them to focus on core agent logic by abstracting away the intricacies of function calling, server integrations, and multi-channel deployment. The platform offers a streamlined approach to building and deploying sophisticated AI agents.

How It Works

The core of MCP-Handle is the Strata MCP router, which dynamically orchestrates agent tooling, ensuring agents only access necessary functions. It integrates over 100 first-party MCP server implementations spanning SaaS, data, communications, and infrastructure. Production-ready clients for Discord, Slack, WhatsApp, CLI, and web are available via an official SDK. Observability is provided by the embedded MCP Handle Status service, featuring a Go/React backend and frontend for rich health and analytics insights.

Quick Start & Requirements

Installation requires Python 3.12+, Node.js 18+, and Go 1.20+. Docker is recommended. After cloning the repository (git clone https://github.com/WeatherPal-AI/MCP-handle.git), dependencies can be installed selectively using uv pip install -r requirements.txt for Strata and uv sync for clients. Strata can be launched locally from the open-strata directory using uv run strata --help. The MCP Handle Status dashboard can be started via the ./scripts/start_status_service.sh script. Comprehensive documentation is available at https://www.mcp-handle.com/docs.

Highlighted Details

  • Features a catalog of over 100 first-party MCP server integrations.
  • Provides production-grade, multi-channel MCP clients (Discord, Slack, WhatsApp, CLI, Web).
  • Includes an embedded MCP Handle Status service for real-time health checks and analytics.
  • Employs Strata, a progressive MCP router for dynamic tool orchestration.

Maintenance & Community

The project is maintained by WeatherPal-AI (低温宝). Open issues and roadmap items are tracked on the GitHub repository, encouraging community discussion and feature requests to foster an open and agent-friendly ecosystem. Further information is available on the project website: https://www.mcp-handle.com.

Licensing & Compatibility

The root license for MCP-Handle is Apache-2.0, which is permissive for commercial use and linking within closed-source projects. Portions of the embedded MCP Handle Status component, sourced from an open project by JustSong, retain their original MIT license.

Limitations & Caveats

The provided README does not explicitly detail known limitations, alpha status, or specific caveats regarding platform support or feature completeness.

Health Check
Last Commit

2 months ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
8 stars in the last 30 days

Explore Similar Projects

Starred by Lilian Weng Lilian Weng(Cofounder of Thinking Machines Lab), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
59 more.

AutoGPT by Significant-Gravitas

0.1%
181k
AI agent platform for building, deploying, and running autonomous workflows
Created 2 years ago
Updated 2 days ago
Feedback? Help us improve.